The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
A blank invoice field should stay blank until there's evidence to fill it.
At Procys, I work on document extraction that combines OCR, LLM layout reasoning, deterministic validation and exception review.
A test I'd use is an otherwise readable invoice with its tax amount removed. Does the workflow preserve 'not found' and route it for review, or silently insert 0.00 because the next system expects a number?
I want reviewers to see the source and the uncertainty before that record moves downstream.
kapilchauhan.netlify.app
Procys: Document intelligence | Kapil Chauhan
Production LLM agents for document processing and identity verification
blank until theres evidence. more extraction tools need that rule
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
One number is a poor release gate for document AI. An invoice extractor can score well overall and still miss the tax value that sends a bad record downstream. At Procys, I work on a pipeline that pairs OCR and LLM reasoning with deterministic checks on headers, line items and tax. I look at failures by field and keep uncertain values tied to their source so a reviewer can resolve them. Case: https://kapilchauhan.netlify.app/case/procys.html
kapilchauhan.netlify.app
Procys: Document intelligence | Kapil Chauhan
Production LLM agents for document processing and identity verification
Then: 1 month, 1 template.
Now: 1 week, 15 templates.
Same designer, different workflow.
I wrote up how I built no-code.supply: fifteen website templates, each with its own brand, in HTML and React, and some in Framer too. Claude Code did most of the typing. I did the directing.
no-code.supply
How I built 15 website templates with an AI coding agent in a week
How I built 15 AI-ready website templates with Claude Code in a week: the workflow, the quality bar, and why a template is only the starting point.
Going from one template a month to fifteen a week is wild. How much of the design direction did you still do by hand?
An AI-built app can work perfectly while any stranger can read its customers' data. Nothing on screen shows it.
Ask whoever built it: which tables hold user data, and what stops a logged-out stranger from reading each one? A good answer is a list. "It should be fine" means nobody has checked.
Andrés, this is the check most founders never run, because nothing breaks until someone looks. Asking for the list of tables and who can read each one is a test any owner can do without writing code. Row level access belongs on the launch checklist, not the cleanup list.
